Linux Advanced Routing and Traffic Control list
 help / color / mirror / Atom feed
* Re: Re: [LARTC] a question about TBF
@ 2002-06-04  4:36 Alexey Talikov
  0 siblings, 0 replies; only message in thread
From: Alexey Talikov @ 2002-06-04  4:36 UTC (permalink / raw)
  To: lartc

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="windows-1252", Size: 2722 bytes --]

Read shapter 
9.2.2.1. Parameters & usage in Advanced Routing HOWTO

mpu
A zero-sized packet does not use zero bandwidth. For ethernet, no packet uses less than 64 bytes. 
The Minimum Packet Unit determines the minimal token usage for a packet



15.02.2000 8:37:10, Huang Xin Gang <hxgang@csnet4.cs.tsinghua.edu.cn> wrote:

>Alexey Talikov,hello!
>
>Thanks for your help!
>But my problem is still here.I found that if a packet is too short,the tick value which 
corresponds to it in the "rtab" is zero.That means the packet doesn't consume any tokens when it's 
being sent.
>
>Is my knowledge right?
>
>
>==== 2002-06-03 09:09:00 you wrote:===>
>>Increase your burst it value at list MTU i.e 1500 byte 
>>
>>rate=ST*burst (ST system timer 100HZ for intel/amd 1024 for alpha)
>>       rate
>>burst=------- and burst>MTU
>>        ST
>>
>>See: Advanced routing HOWTO and for more details 
>>Short Evaluation of Linux's TBF Queueing Discipline. Kurt Wagner 17 May 2001 
>>
>>03.06.2002 7:27:30, Huang Xin Gang <hxgang@csnet4.cs.tsinghua.edu.cn> wrote:
>>
>>>LARTC£¬hello£¡
>>>
>>>I set the command following:
>>>
>>>tc qdisc add dev eth0 root tbf rate 100kbit latency 50ms burst 120
>>>
>>>and then I send flow with speed of 115.2kbit, and if all the packets sent is only 120bytes,the 
>>above command is useless.
>>>
>>>I thinks because the time occupied when sent a packet only 120 bytes is 120*8/(100*1024)<10ms,
>>>but Linux system produces a tick every 10ms,so every time when a packet only 120 bytes 
>>>is being sent, the "toks" equals to zero always, and this packet can be sent immediately.
>>>
>>>all the packets are sent immediately, then the speed is not limited to 100kbit.
>>>
>>>How can I deal with this problem?
>>>
>>>¡¡¡¡¡¡best regards!
>>>
>>> 				
>>>¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡Huang Xin Gang
>>>¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡hxgang@csnet4.cs.tsinghua.edu.cn
>>>¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡¡2002-06-03
>>>,\x04S
>>>f¢–)à–+-ü°\x11L)šŠYš?jya¶Ú?þf¢–f§vÏZž_æj)fj?åŠËbú?•ªíps–Lèm¶Ÿ?•ªírŠà
>>
>>-----------------------------------
>>mailto:alexey_talikov@texlab.com.uz
>>BR
>>Alexey Talikov
>>FORTEK
>>-----------------------------------
>
>= = = = = = = = = = = = = = = = = = = >			
>
>                    best regards!
>				 
>               Huang Xin Gang
>               hxgang@csnet4.cs.tsinghua.edu.cn
>					2000-02-15 

-----------------------------------
mailto:alexey_talikov@texlab.com.uz
BR
Alexey Talikov
FORTEK
-----------------------------------


_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2002-06-04  4:36 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2002-06-04  4:36 Re: [LARTC] a question about TBF Alexey Talikov

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox